Project
Managed AWS service for deploying and scaling OpenSearch clusters, used for search, log analytics, and vector-based applications.
Amazon OpenSearch Service needs about 1.3 TB of resident RAM for 100 million 1,536-dimension FP32 vectors with one replica, a dev.to sizing post calculates. Raw vector values are about 98% of each entry, so the encoding picked before ingestion decides most of that memory and the node count behind it.
Reality
A new AWS walkthrough moves a three-backend healthcare agent off ECS with Fargate by wrapping the same code in a runtime decorator. It changes the reasoning model in the same step, so the two versions cannot be diffed for cost.
Reality
AWS's comparison of the three customer-managed backends credits OpenSearch with in-memory speed and S3 Vectors with sub-second queries at up to 90 percent lower storage cost. The Aurora spec sets a ceiling your embedding model has to fit under.
Reality
A Savings Plan and a Reserved Instance buy the same discount ceiling. Only one of them follows your workload. The residual RI portfolio now comes down to Redshift nodes and OpenSearch.
Reality
Amazon OpenSearch Service now returns interactive visualizations inside MCP tool calls. The claim is that the browser tab, not the query, is what costs an engineer time.
Reality